interactive_figures.ipynb

Make large interactive figures for web viewing using altair with the Nipah RBP DMS data

• Written by Brendan Larsen

# this cell is tagged as parameters for `papermill` parameterization
#input configs
altair_config = None
nipah_config = None

#E2 specific files
func_scores_E2_file = None
binding_E2_file = None
#E3 specific files
func_scores_E3_file = None
binding_E3_file = None

#merged_files
merged_df_file = None
concat_df_file = None

#output plots
output_corr = None
entry_binding_corr_plot_E2_output = None
entry_binding_corr_plot_E3_output = None
corr_entry_binding_large_output = None
combined_binding_output = None
entry_by_site_plot_e2_output = None
entry_by_site_plot_e3_output = None
entry_by_site_plot_e2_bar_plot = None
binding_letter_plot = None

# Parameters
altair_config = "data/custom_analyses_data/interactive_theme.py"
nipah_config = "nipah_config.yaml"
func_scores_E2_file = "results/filtered_data/entry/e2_entry_filtered.csv"
binding_E2_file = "results/filtered_data/binding/e2_binding_filtered.csv"
func_scores_E3_file = "results/filtered_data/entry/e3_entry_filtered.csv"
binding_E3_file = "results/filtered_data/binding/e3_binding_filtered.csv"
merged_df_file = "results/filtered_data/entry/e2_e3_entry_filter_merged.csv"
concat_df_file = "results/filtered_data/entry/e2_e3_entry_filter_concat.csv"
output_corr = "results/images/corr_heatmap.html"
entry_binding_corr_plot_E2_output = "results/images/entry_binding_corr_plot_E2.html"
entry_binding_corr_plot_E3_output = "results/images/entry_binding_corr_plot_E3.html"
corr_entry_binding_large_output = "results/images/corr_entry_binding_large.html"
combined_binding_output = "results/images/combined_binding.html"
entry_by_site_plot_e2_output = "results/images/entry_by_site_plot_e2.html"
entry_by_site_plot_e3_output = "results/images/entry_by_site_plot_e3.html"
entry_by_site_plot_e2_bar_plot = "results/images/entry_by_site_plot_e2_bar_plot.html"
binding_letter_plot = "results/images/binding_letter_plot.html"

Import modules

import math
import os
import re
import altair as alt
import numpy as np
import pandas as pd
import scipy.stats
import yaml

Set working directory

# allow more rows for Altair
_ = alt.data_transformers.disable_max_rows()

if os.getcwd() == '/fh/fast/bloom_j/computational_notebooks/blarsen/2023/Nipah_Malaysia_RBP_DMS/':
    pass
    print("Already in correct directory")
else:
    os.chdir("/fh/fast/bloom_j/computational_notebooks/blarsen/2023/Nipah_Malaysia_RBP_DMS/")
    print("Setup in correct directory")

Setup in correct directory

Setup input file paths for running notebook interactively

if nipah_config is None:
    #input files
    altair_config = 'data/custom_analyses_data/interactive_theme.py'
    nipah_config = 'nipah_config.yaml'
    
    func_scores_E2_file = "results/filtered_data/entry/e2_entry_filtered.csv"
    binding_E2_file = "results/filtered_data/binding/e2_binding_filtered.csv"
    
    func_scores_E3_file = "results/filtered_data/entry/e3_entry_filtered.csv"
    binding_E3_file = "results/filtered_data/binding/e3_binding_filtered.csv"
    
    antibody_file = 'results/filtered_data/escape/mab_filter_concat.csv'
    merged_df_file = 'results/filtered_data/entry/e2_e3_entry_filter_merged.csv'
    concat_df_file = 'results/filtered_data/entry/e2_e3_entry_filter_concat.csv'

Read config files

if altair_config:
    with open(altair_config, 'r') as file:
        exec(file.read())

with open(nipah_config) as f:
    config = yaml.safe_load(f)

Import filtered data

merged_df = pd.read_csv(merged_df_file) #merged entry scores 
display(merged_df.head(3))
concat_df = pd.read_csv(concat_df_file) #concat entry scores
display(concat_df.head(3))

	site	wildtype	mutant	effect_E2	effect_std_E2	times_seen_E2	n_selections_E2	cell_type_E2	wildtype_site_E2	wt_type_E2	mutant_type_E2	effect_E3	effect_std_E3	times_seen_E3	n_selections_E3	cell_type_E3	wildtype_site_E3	wt_type_E3	mutant_type_E3
0	71	Q	C	-1.702	0.1865	4.625	8.0	CHO-bEFNB2	Q71	hydrophilic	special	-0.7227	0.7828	3.000	7.0	CHO-bEFNB3	Q71	hydrophilic	special
1	71	Q	E	-1.199	0.3996	5.250	8.0	CHO-bEFNB2	Q71	hydrophilic	negative	-0.2482	0.9791	4.571	7.0	CHO-bEFNB3	Q71	hydrophilic	negative
2	71	Q	F	-0.947	0.6969	4.625	8.0	CHO-bEFNB2	Q71	hydrophilic	aromatic	-0.4973	0.3080	3.286	7.0	CHO-bEFNB3	Q71	hydrophilic	aromatic

	site	wildtype	mutant	effect	effect_std	times_seen	n_selections	cell_type	wildtype_site	wt_type	mutant_type
0	71	Q	C	-1.702	0.1865	4.625	8	CHO-bEFNB2	Q71	hydrophilic	special
1	71	Q	E	-1.199	0.3996	5.250	8	CHO-bEFNB2	Q71	hydrophilic	negative
2	71	Q	F	-0.947	0.6969	4.625	8	CHO-bEFNB2	Q71	hydrophilic	aromatic

Merge data and make dataframes for plotting

# Read filtered cell entry data
def read_func_data(file,name):
    effect_df = pd.read_csv(file)
    effect_df = effect_df[['site','wildtype','mutant','effect']]
    effect_df['cell_type'] = name
    return effect_df

# Call func to read in cell entry data
e2_func_df = read_func_data(func_scores_E2_file, 'CHO-bEFNB2')
e3_func_df = read_func_data(func_scores_E3_file, 'CHO-bEFNB3')

# Read filtered binding data
def read_binding_data(file,name):
    binding_df = pd.read_csv(file)
    binding_df = binding_df[['site','wildtype','mutant','binding_mean','mutant_type']]
    binding_df['cell_type'] = name
    return binding_df

# Call func to read in binding data
e2_bind_df = read_binding_data(binding_E2_file,'CHO-bEFNB2')
e3_bind_df = read_binding_data(binding_E3_file,'CHO-bEFNB3')

# Concat binding and func data, then merge
def concat_dfs(bind1,bind2,entry1,entry2):
    combo_bind_df = pd.concat([bind1,bind2])
    combo_entry_df = pd.concat([entry1,entry2])
    total_merged = pd.merge(combo_bind_df,combo_entry_df,on=['site','wildtype','mutant','cell_type'],how='outer')
    return total_merged

final_merged_df = concat_dfs(e2_bind_df,e3_bind_df,e2_func_df,e3_func_df)

### Ok, now I have different inputs ready to go for plotting. Lets review
# I have my different entry dataframes
display(e2_func_df.head(2))
display(e3_func_df.head(2))
display(concat_df.head(2))
display(merged_df.head(2))
display(final_merged_df.head(2))

	site	wildtype	mutant	effect	cell_type
0	71	Q	C	-1.702	CHO-bEFNB2
1	71	Q	E	-1.199	CHO-bEFNB2

	site	wildtype	mutant	effect	cell_type
0	71	Q	C	-0.7227	CHO-bEFNB3
1	71	Q	D	-0.3884	CHO-bEFNB3

	site	wildtype	mutant	effect	effect_std	times_seen	n_selections	cell_type	wildtype_site	wt_type	mutant_type
0	71	Q	C	-1.702	0.1865	4.625	8	CHO-bEFNB2	Q71	hydrophilic	special
1	71	Q	E	-1.199	0.3996	5.250	8	CHO-bEFNB2	Q71	hydrophilic	negative

	site	wildtype	mutant	effect_E2	effect_std_E2	times_seen_E2	n_selections_E2	cell_type_E2	wildtype_site_E2	wt_type_E2	mutant_type_E2	effect_E3	effect_std_E3	times_seen_E3	n_selections_E3	cell_type_E3	wildtype_site_E3	wt_type_E3	mutant_type_E3
0	71	Q	C	-1.702	0.1865	4.625	8.0	CHO-bEFNB2	Q71	hydrophilic	special	-0.7227	0.7828	3.000	7.0	CHO-bEFNB3	Q71	hydrophilic	special
1	71	Q	E	-1.199	0.3996	5.250	8.0	CHO-bEFNB2	Q71	hydrophilic	negative	-0.2482	0.9791	4.571	7.0	CHO-bEFNB3	Q71	hydrophilic	negative

	site	wildtype	mutant	binding_mean	mutant_type	cell_type	effect
0	71	Q	E	0.1659	negative	CHO-bEFNB2	-1.199
1	71	Q	F	-0.3429	aromatic	CHO-bEFNB2	-0.947

Now assign RBP region to the dataframe

def find_domain(df):
    barrel_ranges = {
        "Stalk": list(range(70, 148)),
        "Neck": list(range(148, 166)),
        "Linker": list(range(166, 178)),
        "Head": list(range(178, 602)),
    }
    agg_means = []
    # For each barrel, filter the site_means dataframe to the sites belonging to that barrel and then store the means
    for barrel, sites in barrel_ranges.items():
        subset = df[df["site"].isin(sites)]
        for _, row in subset.iterrows():
            agg_means.append(
                {
                    "site": row["site"],
                    "wildtype": row["wildtype"],
                    "mutant": row["mutant"],
                    "region": barrel,
                    "binding_mean": row["binding_mean"],
                    "effect": row['effect'],
                    "cell_type": row["cell_type"],
                    "mutant_type": row["mutant_type"]
                }
            )
        agg_means_df = pd.DataFrame(agg_means)
    return agg_means_df
# Call function above
binding_entry_concat_df = find_domain(final_merged_df)
display(binding_entry_concat_df)

	site	wildtype	mutant	region	binding_mean	effect	cell_type	mutant_type
0	71	Q	E	Stalk	0.16590	-1.19900	CHO-bEFNB2	negative
1	71	Q	F	Stalk	-0.34290	-0.94700	CHO-bEFNB2	aromatic
2	71	Q	G	Stalk	0.46570	-1.37400	CHO-bEFNB2	special
3	71	Q	H	Stalk	0.02003	-0.40780	CHO-bEFNB2	positive
4	71	Q	K	Stalk	0.08932	-0.05105	CHO-bEFNB2	positive
...	...	...	...	...	...	...	...	...
19398	601	C	F	Head	NaN	-1.66700	CHO-bEFNB3	NaN
19399	601	C	G	Head	NaN	-2.04700	CHO-bEFNB3	NaN
19400	601	C	I	Head	NaN	-0.75770	CHO-bEFNB3	NaN
19401	601	C	P	Head	NaN	-1.52300	CHO-bEFNB3	NaN
19402	601	C	V	Head	NaN	0.01403	CHO-bEFNB3	NaN

19403 rows × 8 columns

Make a site-averaged dataframe of cell entry and binding

### Make a dataframe with the averaged values of mutants at each site
tmp_df = binding_entry_concat_df.groupby(['site','cell_type'])[['effect','binding_mean']].mean().reset_index()
subset_df = binding_entry_concat_df.drop_duplicates(['site','wildtype','region'])

mean_df = pd.merge(tmp_df,subset_df[['site','wildtype','region']],on='site',how='left')
display(mean_df.head(5))

	site	cell_type	effect	binding_mean	wildtype	region
0	71	CHO-bEFNB2	-1.145872	0.146081	Q	Stalk
1	71	CHO-bEFNB3	-0.616870	-0.111348	Q	Stalk
2	72	CHO-bEFNB2	-1.221033	0.035927	N	Stalk
3	72	CHO-bEFNB3	-0.759448	-0.103486	N	Stalk
4	73	CHO-bEFNB2	-0.736845	0.130661	Y	Stalk

Make a pivot table for plotting certain data

display(binding_entry_concat_df)

	site	wildtype	mutant	region	binding_mean	effect	cell_type	mutant_type
0	71	Q	E	Stalk	0.16590	-1.19900	CHO-bEFNB2	negative
1	71	Q	F	Stalk	-0.34290	-0.94700	CHO-bEFNB2	aromatic
2	71	Q	G	Stalk	0.46570	-1.37400	CHO-bEFNB2	special
3	71	Q	H	Stalk	0.02003	-0.40780	CHO-bEFNB2	positive
4	71	Q	K	Stalk	0.08932	-0.05105	CHO-bEFNB2	positive
...	...	...	...	...	...	...	...	...
19398	601	C	F	Head	NaN	-1.66700	CHO-bEFNB3	NaN
19399	601	C	G	Head	NaN	-2.04700	CHO-bEFNB3	NaN
19400	601	C	I	Head	NaN	-0.75770	CHO-bEFNB3	NaN
19401	601	C	P	Head	NaN	-1.52300	CHO-bEFNB3	NaN
19402	601	C	V	Head	NaN	0.01403	CHO-bEFNB3	NaN

19403 rows × 8 columns

#Now make a pivot table for some graphs
df_pivot = binding_entry_concat_df.pivot_table(index=['region', 'site', 'wildtype','mutant'], 
                          columns='cell_type', 
                          values=['effect', 'binding_mean','mutant_type'],
                          aggfunc='first').reset_index()

# Flatten df
df_pivot.columns = ['_'.join(col).strip() if col[1] else col[0] for col in df_pivot.columns.values]
# rename
df_pivot.rename(columns={
    'effect_CHO-bEFNB2': 'effect_E2',
    'effect_CHO-bEFNB3': 'effect_E3',
    'binding_mean_CHO-bEFNB2': 'binding_E2',
    'binding_mean_CHO-bEFNB3': 'binding_E3'
}, inplace=True)

display(df_pivot.sort_values(by='site').head(5))

	region	site	wildtype	mutant	binding_E2	binding_E3	effect_E2	effect_E3	mutant_type_CHO-bEFNB2	mutant_type_CHO-bEFNB3
8517	Stalk	71	Q	L	NaN	-0.03759	NaN	-0.1305	NaN	hydrophobic
8512	Stalk	71	Q	F	-0.3429	-0.03982	-0.947	-0.4973	aromatic	aromatic
8511	Stalk	71	Q	E	0.1659	-0.35270	-1.199	-0.2482	negative	negative
8510	Stalk	71	Q	D	NaN	-0.29370	NaN	-0.3884	NaN	negative
8513	Stalk	71	Q	G	0.4657	-0.04107	-1.374	-1.3310	special	special

Make plots

Make heatmap of correlations between entry in CHO-bEFNB2 and CHO-bEFNB3

def correlation_heatmap(df):
    chart = (
        alt.Chart(df,title=alt.Title('Effects of RBP Mutations on Cell Entry',subtitle='Between CHO cells expressing bat EFNB2 or EFNB3'))
        .mark_rect()
        .encode(
            alt.X("effect_E2", title="RBP mutant entry in CHO-bEFNB2",axis=alt.Axis(values=[-4,-3,-2,-1,0,1])).bin(maxbins=75),
            alt.Y("effect_E3", title="RBP mutant entry in CHO-bEFNB3",axis=alt.Axis(values=[-4,-3,-2,-1,0,1])).bin(maxbins=75),
            alt.Color('count():Q',title='Count').scale(type='log'),
            tooltip=['count()'],
        )
    ).properties(
    height=400,
    width=400,
).configure_legend(
    padding=2,
    orient='top-left', #"left", "right", "top", "bottom", "top-left", "top-right", "bottom-left", "bottom-right", "none"
    labelFontSize=16,
    titlePadding=2,
    symbolSize=100,
)

    return chart
corr_heatmap = correlation_heatmap(merged_df)
corr_heatmap.display()
if entry_by_site_plot_e3_output is not None:
    corr_heatmap.save(output_corr)

Make interactive plot linking individual binding and entry effects with top 10 summed binding and entry

def plot_entry_binding_interactive(df,name):
    #find contact sites
    df_copy = df.copy()
    df_copy.loc[:, 'is_contact'] = df_copy['site'].isin(config['contact_sites'])
    
    # make a brush for interactivity
    brush = alt.selection_interval() 
    
    #scatter plot
    chart = alt.Chart(df_copy).mark_point(filled=True,size=50).encode(
            alt.X("effect", title="Cell Entry", axis=alt.Axis(values=[-2,-1,0,1])),
            alt.Y("binding_mean", title="Binding", axis=alt.Axis(values=[-4,-2,0,2])),
            color=alt.condition(brush, 'is_contact', alt.value('lightgray')),  
            tooltip=["site", "wildtype", "mutant", "binding_mean","effect"]  
    ).add_params(
        brush
    ).properties(
        width=400, 
        height=400
    )  
    
    # Create a bar chart showing the sum of binding_median values for the top 10 sites filtered by the selection.
    bars_binding = alt.Chart(df_copy).transform_filter(
        brush  # Apply the selection filter to include only selected data.
    ).transform_aggregate(
        binding_aggr='sum(binding_mean)',  # Aggregate data by summing up binding for selected sites
        groupby=['site', 'is_contact']
    ).transform_window(
        rank='rank(binding_aggr)',  # Rank sites based on the aggregated sum.
        sort=[alt.SortField('binding_aggr', order='descending')]  # Sort by descending order of sum.
    ).transform_filter(
        alt.datum.rank <= 10  # Filter to keep only the top 10 ranked sites.
    ).mark_bar().encode(
        alt.X('site:N', sort='-y', title='Site', axis=alt.Axis(labelAngle=-90)),  # Encode site names on x-axis with custom sorting and label angle.
        alt.Y('binding_aggr:Q', title='Binding'),  # Encode aggregated sum on y-axis.
        color=alt.Color('is_contact', title='Receptor Contact Site')  # Color bars based on whether they are contact sites.
    ).properties(
        width=200, 
        height=50
    )  
    
    # Similar to the bars chart for binding_median, but aggregates and ranks sites based on the 'effect' value.
    bars_effect = alt.Chart(df_copy,title='Top 10').transform_filter(
        brush
    ).transform_aggregate(
        effect_aggr='sum(effect)',
        groupby=['site', 'is_contact']
    ).transform_window(
        rank='rank(effect_aggr)',
        sort=[alt.SortField('effect_aggr', order='descending')]
    ).transform_filter(
        alt.datum.rank <= 10
    ).mark_bar().encode(
        x=alt.X('site:N', sort='-y', title='Site', axis=alt.Axis(labelAngle=-90)),
        y=alt.Y('effect_aggr:Q', title='Entry'),
        color=alt.Color('is_contact', title='Receptor Contact Site')
    ).properties(
        width=200, 
        height=50
    )
    
    # Combine the scatter plot with the two bar charts (stacked vertically and placed side by side).
    combined_chart = chart & (bars_effect | bars_binding)
    combined_chart = combined_chart.properties(
        title={
            "text": f"Correlation of Cell Entry and Binding for {name}", 
            "subtitle": ["Draw box in scatterplot to show the top 10 sites by summed binding or entry"],
        }
    )
    return combined_chart

entry_binding_corr_plot_E2 = plot_entry_binding_interactive(final_merged_df.query('cell_type == "CHO-bEFNB2"'),'bEFNB2')
entry_binding_corr_plot_E2.display()
if entry_by_site_plot_e3_output is not None:
    entry_binding_corr_plot_E2.save(entry_binding_corr_plot_E2_output)

Now do the same above for for EFNB3

entry_binding_corr_plot_E3 = plot_entry_binding_interactive(final_merged_df.query('cell_type == "CHO-bEFNB3"'),'bEFNB3')
entry_binding_corr_plot_E3.display()
if entry_by_site_plot_e3_output is not None:
    entry_binding_corr_plot_E3.save(entry_binding_corr_plot_E3_output)

Make correlation plots for entry and binding for both efnb2 and efnb3 colored by protein region

def correlation_plot(df):
    options = ['Stalk', 'Neck', 'Linker','Head']
    labels = [option + ' ' for option in options]
    df = df.round(2)

    #setup interactivity
    input_dropdown = alt.binding_radio(
        options=options + [None],
        labels=labels + ['All'],
        name='Region: '
    )
    
    selection = alt.selection_point(
        fields=['region'],
        bind=input_dropdown,
    )    
    
    color = alt.condition(
        selection,
        alt.Color('region:N',scale=alt.Scale(domain=options),title='Region'),
        alt.value('lightgray'),
    )

    opacity = alt.condition(
        selection,
        alt.value(1),
        alt.value(0.5)
    )
    
    #make chart
    effect_chart = (
        alt.Chart(df,title='Cell entry')
        .mark_point(size=30,opacity=1,filled=True)
        .encode(
            alt.X("effect_E2", title="Entry in CHO-bEFNB2",axis=alt.Axis(tickCount=4)),
            alt.Y("effect_E3", title="Entry in CHO-bEFNB3",axis=alt.Axis(tickCount=4)),
            tooltip=['wildtype',"site", "mutant",'effect_E2','effect_E3','binding_E2','binding_E3'],
            opacity=opacity,
            color=color,
        )
    ).properties(
        height=350,
        width=350
    )
    
    binding_chart = (
        alt.Chart(df,title='Receptor Binding')
        .mark_point(size=30,opacity=1,filled=True)
        .encode(
            alt.X("binding_E2", title="bEFNB2 Binding",axis=alt.Axis(tickCount=4)),
            alt.Y("binding_E3", title="bEFNB3 Binding",axis=alt.Axis(tickCount=4)),
            tooltip=['wildtype',"site", "mutant",'effect_E2','effect_E3','binding_E2','binding_E3'],
            color=color,
            opacity=opacity
        )
    ).properties(
        height=350,
        width=350
    )
    #combine charts
    combined_chart = effect_chart | binding_chart
    combined_chart=combined_chart.add_params(selection).properties(
        title=alt.Title('Correlations Between Entry and Binding for bEFNB2 and bEFNB3',
                        subtitle=['Select radio button to see mutants highlighted or hover over points to see more information'])
    )
    return combined_chart

# Call function above and save
corr_entry_binding_large = correlation_plot(df_pivot)
corr_entry_binding_large.display()
if entry_by_site_plot_e3_output is not None:
    corr_entry_binding_large.save(corr_entry_binding_large_output)

Make figures showing only binding

def make_custom_binding_figure(df,name):
    brush = alt.selection_interval() #define selection brush
    custom_order = ["Stalk", "Neck", "Linker", "Head"]

    chart = alt.Chart(df,title=alt.Title(f'{name}')).mark_point(opacity=0.3,filled=True).encode(
            alt.X(
                "binding_mean",
                title=f"Binding",
                axis=alt.Axis(tickCount=4),
            ),
            alt.Y(
                "region:O",
                sort=custom_order,
                title="RBP Region",
            ),
            
            yOffset="random:Q",
            tooltip=["region", "binding_mean", "site", "mutant"],
            color=alt.condition(brush, 'region', alt.value('lightgray')),
        ).transform_calculate(random="sqrt(-1*log(random()))*cos(2*PI*random())").properties(height=200,width=400).add_params(brush)
    
    bars = alt.Chart(df).transform_filter(
            brush
        ).transform_aggregate(
            binding_aggr='sum(binding_mean)',
            groupby=['site', 'region']
        ).transform_window(
            rank='rank(binding_aggr)',
            sort=[alt.SortField('binding_aggr', order='descending')]
        ).transform_filter(
            alt.datum.rank <= 10
        ).mark_bar().encode(
            y=alt.Y('binding_aggr:Q',title='Binding'),
            x=alt.X('site:N', sort='-y',title='Site'),
            color=alt.Color('region',title='Region')
        ).properties(height=50,width=400)
    combined_chart = chart & bars 
    combined_chart
    return combined_chart

#make individual bEFNB2 plot
efnb2_binding_region = make_custom_binding_figure(binding_entry_concat_df.query('cell_type == "CHO-bEFNB2"'),'bEFNB2')
#efnb2_binding_region.display()

#make individual bEFNB3 plot
efnb3_binding_region = make_custom_binding_figure(binding_entry_concat_df.query('cell_type == "CHO-bEFNB3"'),'bEFNB3')
#efnb3_binding_region.display()

# combine the plots
combined_binding = (efnb2_binding_region | efnb3_binding_region).properties(
    title=alt.Title('Receptor Binding by RBP mutant',
    subtitle='Draw boxes around scatter plots to see sites with the top 10 summed mutant binding')
)

combined_binding.display()
if entry_by_site_plot_e3_output is not None:
    combined_binding.save(combined_binding_output)

Make interactive plots of average effects of mutants by site

def entry_by_site(df):
    df = df.round(2)
    custom_order = ["Stalk", "Neck", "Linker", "Head"] #custom order for color legend

    variant_selector = alt.selection_point(
        on="mouseover", empty=False,nearest=True, fields=["site"], value=1
    )
    
    chart = (
        alt.Chart(df)
        .mark_bar(opacity=1,stroke='black')
        .encode(
            alt.X("site:N", title='Site',axis=alt.Axis(labelAngle=-90,values=[100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600],tickCount=11,grid=True)),
            alt.Y("effect", title="Mean entry"),
            tooltip=['wildtype',"site", "effect","region"],
            color=alt.Color('region',sort=custom_order,title='Region'),
            strokeWidth=alt.condition(
                    variant_selector, alt.value(1), alt.value(0)
                ),
            row=alt.Row('cell_type',title=None,header=alt.Header(labelFontSize=16,labelFontWeight='bold'))
        )
    ).properties(
        width=800,
        height=150
    )
    combined_chart = chart.properties(
        title=alt.Title('Average Cell Entry of Mutants at Each Site',
        subtitle=['Hover mouse over bars to view information about cell entry'])
    ).add_params(variant_selector)
    
    return combined_chart

entry_by_site_plot = entry_by_site(mean_df)
entry_by_site_plot.display()
#entry_by_site_plot.save('results/images/entry_by_site_plot.html')

def binding_by_site(df):
    #Site 500 is filtered out so I need to add a dummy value so it shows up on axis:
    data = {
        'site': [500],
        'cell_type': ['CHO-bEFNB2'],
        'effect': [0],
        'binding_mean': [0],
        'wildtype': [None],  # Use None for missing values, or '' for an empty string
        'region': ['Head']
    }
    # Create DataFrame
    dummy_data = pd.DataFrame(data)
    df = pd.concat([df, dummy_data])

    
    df = df.round(2)
    custom_order = ["Stalk", "Neck", "Linker", "Head"] #custom order for color legend

    variant_selector = alt.selection_point(
        on="mouseover", empty=False,nearest=True, fields=["site"], value=1
    )
    
    chart = (
        alt.Chart(df)
        .mark_bar(opacity=1,stroke='black')
        .encode(
            alt.X("site:N", title='Site',axis=alt.Axis(labelAngle=-90,values=[100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600],tickCount=11,grid=True)),
            alt.Y("binding_mean", title="Mean binding"),
            tooltip=['wildtype',"site", "effect","region"],
            color=alt.Color('region',sort=custom_order,title='Region'),
            strokeWidth=alt.condition(
                    variant_selector, alt.value(1), alt.value(0)
                ),
            row=alt.Row('cell_type',title=None,header=alt.Header(labelFontSize=16,labelFontWeight='bold'))
        )
    ).properties(
        width=800,
        height=150
    )
    combined_chart = chart.properties(
        title=alt.Title('Average Receptor Binding of Mutants at Each Site',
        subtitle=['Hover mouse over bars to view information about cell entry'])
    ).add_params(variant_selector).resolve_scale(y='independent')
    
    return combined_chart

#call function above
entry_by_site_plot = binding_by_site(mean_df)
entry_by_site_plot.display()
#entry_by_site_plot.save('results/images/entry_by_site_plot.html')

Make interactive chart similar to above but also show individual mutations in heatmaps

def entry_by_site(df,name,effect):
    # make an empty dataframe with every possible mutation so empty values still get plotted
    amino_acid_order = ["R","K","H","D","E","Q","N","S","T","Y","W","F","A","I","L","M","V","G","P","C"]
    sites = range(71, 603)
    data = [{"site": site, "mutant": aa} for site in sites for aa in amino_acid_order]
    empty_df = pd.DataFrame(data)
    full_df = pd.merge(empty_df,df,on=['site','mutant'],how='left')
 
    #setup interactive features
    variant_selector = alt.selection_point(
        on="mouseover", empty=False,nearest=True, fields=["site"], value=1
    )
    
    #make base chart
    base = alt.Chart(full_df).add_params(variant_selector)
    #add bar chart of cell entry by site
    chart = base.mark_bar(opacity=1,stroke='black').encode(
            alt.X("site:N", title='Site',axis=alt.Axis(values=[100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600],tickCount=11,grid=True)),
            alt.Y(f"mean({effect})", title="Mean entry"),
            tooltip=["site", "wildtype","region"],
            opacity=alt.condition(variant_selector,alt.value(1),alt.value(0.7)),
            strokeWidth=alt.condition(variant_selector, alt.value(1), alt.value(0)),
            color=alt.Color('region',title='Region')
    ).properties(
        width=800,
        height=200
    )

    #add heatmap below showing effect of mutants on cell entry
    select_bar = alt.Chart(full_df).mark_bar(stroke='black').encode(
        alt.X('mutant:N',title=None,scale=alt.Scale(domain=amino_acid_order)),
        color=alt.Color(f'{effect}',legend=alt.Legend(orient='right',direction='horizontal',titleAlign='center',titleAnchor='middle'),title='Cell entry',scale=alt.Scale(scheme='redblue',domainMid=0,domain=[-4,2]))
    ).transform_filter(
        variant_selector
    ).properties(
        width=400,
        height=10
    )

    #make heatmap have an x for wildtype residue
    select_bar_wildtype = alt.Chart(full_df).mark_text(color="black", text="X", size=10, align="center", baseline="middle").encode(
        alt.X('wildtype:N',title='Amino acid'),
    ).transform_filter(
        variant_selector
    ).transform_filter(
        (alt.datum[effect] != None) #filter out empty data
    ).properties(
        width=400,
        height=10
    )
    # combine heatmap plots
    combined_effects_w_wildtype = alt.layer(select_bar_wildtype,select_bar).resolve_scale(x='shared')

    # combine the bar and heatmaps
    combined_chart = alt.vconcat(chart,combined_effects_w_wildtype).resolve_scale(y='independent',x='independent')
    combined_chart = combined_chart.properties(
        title=alt.Title(f'Entry in {name}',
        subtitle=['Hover over sites to see information about entry of specific mutations'])
    )
    return combined_chart

# call chart function
entry_by_site_plot_e2 = entry_by_site(df_pivot,'CHO-bEFNB2','effect_E2')
entry_by_site_plot_e2.display()
if entry_by_site_plot_e3_output is not None:
    entry_by_site_plot_e2.save(entry_by_site_plot_e2_output)

# call chart function
entry_by_site_plot_e3 = entry_by_site(df_pivot,'CHO-bEFNB3','effect_E3')
entry_by_site_plot_e3.display()
if entry_by_site_plot_e3_output is not None:
    entry_by_site_plot_e3.save(entry_by_site_plot_e3_output)

combined_entry_by_site = (entry_by_site_plot_e2 & entry_by_site_plot_e3)
combined_entry_by_site.display()

TESTING. Stuff below work in progress

def entry_by_site_test(df,name,effect):
    # make an empty dataframe with every possible mutation so empty values still get plotted
    amino_acid_order = ["R","K","H","D","E","Q","N","S","T","Y","W","F","A","I","L","M","V","G","P","C"]
    sites = range(71, 603)
    data = [{"site": site, "mutant": aa} for site in sites for aa in amino_acid_order]
    empty_df = pd.DataFrame(data)
    full_df = pd.merge(empty_df,df,on=['site','mutant'],how='left')
 
    #setup interactive features
    variant_selector = alt.selection_point(
        on="mouseover", empty=False,nearest=True, fields=["site"], value=1
    )
    
    #make base chart
    base = alt.Chart(full_df).add_params(variant_selector)
    #add bar chart of cell entry by site
    chart = base.mark_bar(opacity=1,stroke='black').encode(
            alt.X("site:N", title='Site',axis=alt.Axis(values=[100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600],tickCount=11,grid=True)),
            alt.Y(f"mean({effect})", title="Mean entry"),
            tooltip=["site", "wildtype","region"],
            opacity=alt.condition(variant_selector,alt.value(1),alt.value(1)),
            strokeWidth=alt.condition(variant_selector, alt.value(1), alt.value(0)),
            color=alt.Color('region',title='Region')
    ).properties(
        width=800,
        height=200
    )

    select_bar = alt.Chart(full_df).mark_bar(stroke='black', color='darkgray').encode(
        alt.X('mutant:N', title=None, scale=alt.Scale(domain=amino_acid_order)),  # Removed sort='-y' here
        alt.Y(f'{effect}', scale=alt.Scale(domain=[-4, 2]), title='Cell entry'),
    ).transform_filter(
        variant_selector
    ).transform_window(
        rank='rank()',
        sort=[alt.SortField(f'{effect}', order='descending')]  # Sort based on the effect values in descending order
    ).properties(
        width=800,
        height=100
    )

    #make heatmap have an x for wildtype residue
    select_bar_wildtype = alt.Chart(full_df).mark_text(color="black", text="X", size=14, align="center", baseline="middle").encode(
        alt.X('wildtype:N',title='Amino acid'),
    ).transform_filter(
        variant_selector
    ).transform_filter(
        (alt.datum[effect] != None) #filter out empty data
    ).properties(
        width=800,
        height=100
    )
    
    # combine heatmap plots
    combined_effects_w_wildtype = alt.layer(select_bar_wildtype,select_bar).resolve_scale(x='shared')

    # combine the bar and heatmaps
    combined_chart = alt.vconcat(chart,combined_effects_w_wildtype).resolve_scale(y='independent',x='independent')
    combined_chart = combined_chart.properties(
        title=alt.Title(f'Entry in {name}',
        subtitle=['Hover over sites to see information about entry of specific mutations'])
    )
    return combined_chart

entry_by_site_plot_e2_bar = entry_by_site_test(df_pivot,'CHO-bEFNB2','effect_E2')
entry_by_site_plot_e2_bar.display()
if entry_by_site_plot_e3_output is not None:
    entry_by_site_plot_e2_bar.save(entry_by_site_plot_e2_bar_plot)

def make_effect_by_site_with_hover_tooltip(df):
    tmp_df = df.groupby(['cell_type','site'])['effect'].mean().reset_index().round(2)
    
    # Create a selection that chooses the nearest point & selects based on x-value
    nearest = alt.selection_point(nearest=True, on='mouseover',
                            fields=['site'], empty=False)
    
    # The basic line
    line = alt.Chart(tmp_df).mark_line(interpolate='basis',size=1).encode(
        alt.X('site:Q', title='Site',axis=alt.Axis(values=[100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600])),
        alt.Y('effect:Q',title='Mean entry'),
        color=alt.Color('cell_type:N',title='Cell type')
    )
    
    # Transparent selectors across the chart. This is what tells us
    # the x-value of the cursor
    selectors = alt.Chart(tmp_df).mark_point().encode(
        alt.X('site:Q'),
        opacity=alt.value(0),
    ).add_params(
        nearest
    )
    # Draw points on the line, and highlight based on selection
    points = line.mark_point().encode(
        opacity=alt.condition(nearest, alt.value(1), alt.value(0))
    )
    
    # Draw text labels near the points, and highlight based on selection
    text = line.mark_text(align='left', dx=5, dy=-5,fontSize=15).encode(
        text=alt.condition(nearest, 'effect:Q', alt.value(' ')),
        #color=alt.value('black')
    )#.transform_filter(alt.datum.cell_type == 'CHO-EFNB2')
    
    # Draw a rule at the location of the selection
    rules = alt.Chart(tmp_df).mark_rule(color='gray').encode(
        x='site:Q',
    ).transform_filter(
        nearest
    )
    # Put the five layers into a chart and bind the data
    combined_chart = alt.layer(
        line, selectors, points, rules, text
    ).properties(
        width=800, height=200
    )
    return combined_chart

alt_plot = make_effect_by_site_with_hover_tooltip(binding_entry_concat_df)
alt_plot.display()

def plot_affinity_individual_mutants(df,mutant):
    df = df.dropna().round(2).copy()
    x_max = df['binding_E3'].max()
    print(x_max)
    selector = alt.selection_point(
        name="SelectorName",
        fields=['site'],
        bind=alt.binding_range(min=185,max=602,step=1,name='Site'),
        value=[{'site': 492}]
    )
    
    chart = (alt.Chart(df)
        .mark_text(size=20)
        .encode(
            alt.X("binding_E2", title=("bEFNB2 binding"),axis=alt.Axis(tickCount=4),scale=alt.Scale(domain=[-4.5,2])),
            alt.Y("binding_E3", title=("bEFNB3 binding"),axis=alt.Axis(tickCount=4),scale=alt.Scale(domain=[-2,2])),
            alt.Text('mutant'),
            alt.Color('mutant_type_CHO-bEFNB2',title='Mutant type'),
            tooltip=['site','wildtype','binding_E2','binding_E3','effect_E2','effect_E3'],
            
        )
    ).add_params(
        selector
    ).transform_filter(
        selector
    ).properties(
        title='Correlation of effects of amino acid mutations in RBP head on binding to bEFNB2 or bEFNB3',
        height=400,
        width=400
    )
    # Vertical line at x=0
    vline = alt.Chart(pd.DataFrame({'x': [0]})).mark_rule(color='gray',opacity=0.5).encode(x='x:Q')

    # Horizontal line at y=0
    hline = alt.Chart(pd.DataFrame({'y': [0]})).mark_rule(color='gray',opacity=0.5).encode(y='y:Q')

    # Combine the scatter plot with the vertical and horizontal lines
    final_chart = chart + vline + hline

    return final_chart

test_plot = plot_affinity_individual_mutants(df_pivot,306)
test_plot.display()
test_plot.save(binding_letter_plot)

1.26

display(df_pivot)

	region	site	wildtype	mutant	binding_E2	binding_E3	effect_E2	effect_E3	mutant_type_CHO-bEFNB2	mutant_type_CHO-bEFNB3
0	Head	178	V	A	0.7066	0.008861	-0.28470	0.01306	hydrophobic	hydrophobic
1	Head	178	V	C	0.1814	0.451400	0.07725	0.47640	special	special
2	Head	178	V	D	NaN	-0.041930	-2.04100	-1.03800	None	negative
3	Head	178	V	E	NaN	0.142800	-1.74700	-0.41900	None	negative
4	Head	178	V	F	0.5869	0.039550	-1.01900	-0.34260	aromatic	aromatic
...	...	...	...	...	...	...	...	...	...	...
9907	Stalk	147	K	S	0.1344	-0.060950	0.14910	0.13650	hydrophilic	hydrophilic
9908	Stalk	147	K	T	1.0700	-0.052750	-0.43670	-0.79560	hydrophilic	hydrophilic
9909	Stalk	147	K	V	NaN	0.086850	-1.94400	-1.02500	None	hydrophobic
9910	Stalk	147	K	W	NaN	NaN	-2.90900	-2.27500	None	None
9911	Stalk	147	K	Y	NaN	NaN	-2.96300	-1.39500	None	None

9912 rows × 10 columns